Update app.py

app.py

@@ -7,7 +7,7 @@ import logging
 import random  
 import json  
 from datetime import datetime, timedelta  
-import re  
+import hashlib  
 from urllib.parse import quote  
 
 # Configure logging  
@@ -28,39 +28,37 @@ STORY_CACHE = {}
 CACHE_EXPIRY = {}  
 LAST_REQUEST = {}  
 
-# User agents (more diverse selection to avoid pattern detection)  
+# User agents  
 USER_AGENTS = [  
     "Mozilla/5.0 (iPhone; CPU iPhone OS 16_6 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/16.6 Mobile/15E148 Safari/604.1",  
     "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/17.0 Safari/605.1.15",  
-    "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",  
-    "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/118.0.0.0 Safari/537.36",  
-    "Mozilla/5.0 (iPad; CPU OS 16_6 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/16.6 Mobile/15E148 Safari/604.1"  
+    "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"  
 ]  
 
-# The famous Instagram accounts that typically have stories  
-DEMO_ACCOUNTS = [  
-    "arianagrande", "justinbieber", "selenagomez", "kendalljenner",  
-    "kyliejenner", "therock", "kimkardashian", "leomessi", "beyonce",  
-    "taylorswift", "jlo", "kevinhart4real", "kingjames", "champagnepapi",  
-    "kourtneykardash", "neymarjr", "chrisbrownofficial", "kevinhart4real",  
-    "billieeilish", "davidbeckham", "ladygaga", "dualipa", "shawnmendes"  
-]  
-
-# Demo content to use when Instagram rate limits  
+# More diverse demo content for better user experience  
 DEMO_STORIES = {  
-    "arianagrande": [  
-        {"id": "demo1", "type": "image", "url": "https://res.cloudinary.com/demo/image/upload/v1312461204/sample.jpg"},  
-        {"id": "demo2", "type": "video", "url": "https://res.cloudinary.com/demo/video/upload/v1389969025/sample.mp4"}  
+    "type1": [  
+        {"id": "nature1", "type": "image", "url": "https://images.unsplash.com/photo-1682687980961-78fa83781450"},  
+        {"id": "nature2", "type": "image", "url": "https://images.unsplash.com/photo-1709921233257-4d6fad0af5c8"}  
+    ],  
+    "type2": [  
+        {"id": "city1", "type": "image", "url": "https://images.unsplash.com/photo-1710319367362-089a828a423c"},  
+        {"id": "city2", "type": "video", "url": "https://assets.mixkit.co/videos/preview/mixkit-aerial-view-of-city-traffic-at-night-11-large.mp4"}  
+    ],  
+    "type3": [  
+        {"id": "food1", "type": "image", "url": "https://images.unsplash.com/photo-1710170883104-2e9ac8709bb7"},  
+        {"id": "food2", "type": "image", "url": "https://images.unsplash.com/photo-1683009427500-71a13c0dce20"}  
     ],  
-    "justinbieber": [  
-        {"id": "demo3", "type": "image", "url": "https://res.cloudinary.com/demo/image/upload/v1312461204/vegetables.jpg"},  
-        {"id": "demo4", "type": "image", "url": "https://res.cloudinary.com/demo/image/upload/v1312461204/food.jpg"}  
+    "type4": [  
+        {"id": "travel1", "type": "image", "url": "https://images.unsplash.com/photo-1682687982501-1e58ab814714"},  
+        {"id": "travel2", "type": "video", "url": "https://assets.mixkit.co/videos/preview/mixkit-going-down-a-curved-highway-through-a-mountain-range-41576-large.mp4"}  
     ],  
+    "type5": [  
+        {"id": "people1", "type": "image", "url": "https://images.unsplash.com/photo-1710161380135-9b617884d65f"},  
+        {"id": "people2", "type": "video", "url": "https://assets.mixkit.co/videos/preview/mixkit-man-dancing-under-changing-lights-1240-large.mp4"}  
+    ]  
 }  
 
-# For any username not in our demo accounts, we'll return a "does not have stories" error  
-# Instead we'll randomize between these static examples  
-
 def get_cache_key(username):  
     """Generate a cache key from username"""  
     return username.lower()  
@@ -111,15 +109,15 @@ def should_rate_limit_request(username):
     return False  
 
 def get_demo_stories(username):  
-    """Return demo stories for a username"""  
+    """Return demo stories for a username with deterministic but varied selection"""  
     logger.info(f"Using demo stories for {username}")  
     
-    if username.lower() in DEMO_STORIES:  
-        stories = DEMO_STORIES[username.lower()]  
-    else:  
-        # Pick a random set of demo stories  
-        random_account = random.choice(list(DEMO_STORIES.keys()))  
-        stories = DEMO_STORIES[random_account]  
+    # Use hash of username to deterministically select a demo type for each username  
+    # This ensures the same username always gets the same demo content  
+    hash_value = int(hashlib.md5(username.lower().encode()).hexdigest(), 16)  
+    demo_type = f"type{(hash_value % 5) + 1}"  # Get a number between 1-5  
+    
+    stories = DEMO_STORIES[demo_type]  
     
     # Add timestamps to make them seem fresh  
     for story in stories:  
@@ -133,87 +131,97 @@ def get_demo_stories(username):
         "count": len(stories),  
         "username": username,  
         "demo": True,  # Mark as demo content  
+        "note": "Using placeholder content - Instagram API access is currently restricted",  
         "fetched_at": datetime.now().isoformat()  
     }  
     
     return result  
 
-def get_picuki_stories(username):  
-    """Try to get stories from Picuki"""  
+def try_get_real_stories(username):  
+    """Attempt to get real stories using multiple methods"""  
+    # Try method 1: Direct API (very likely to fail due to restrictions)  
     try:  
-        url = f"https://www.picuki.com/profile/{username}"  
+        logger.info(f"Attempting direct API access for {username}")  
+        url = f"https://i.instagram.com/api/v1/feed/user/{username}/story/"  
         headers = {  
-            'User-Agent': random.choice(USER_AGENTS),  
-            'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,*/*;q=0.8',  
-            'Accept-Language': 'en-US,en;q=0.5',  
-            'Referer': 'https://www.google.com/',  
-            'Connection': 'keep-alive',  
-            'Upgrade-Insecure-Requests': '1',  
-            'Sec-Fetch-Dest': 'document',  
-            'Sec-Fetch-Mode': 'navigate',  
-            'Sec-Fetch-Site': 'cross-site',  
-            'Sec-Fetch-User': '?1',  
+            'User-Agent': 'Instagram 219.0.0.12.117 Android',  
+            'Accept-Language': 'en-US',  
         }  
+        response = requests.get(url, headers=headers, timeout=5)  
         
-        response = requests.get(url, headers=headers, timeout=10)  
-        response.raise_for_status()  
-        
-        # Check if there are stories  
-        stories_match = re.search(r'stories-container[^>]*>(.+?)</div>', response.text, re.DOTALL)  
-        if not stories_match:  
-            logger.info(f"No stories found on Picuki for {username}")  
-            return None  
-        
-        stories_html = stories_match.group(1)  
-        
-        # Extract story items  
-        story_items = re.findall(r'<div[^>]*class="story-item[^>]*>(.+?)</div>', stories_html, re.DOTALL)  
-        if not story_items:  
-            logger.info(f"No story items found on Picuki for {username}")  
-            return None  
-        
-        # Process stories  
-        stories = []  
-        for item in story_items:  
-            # Try to extract image URL  
-            img_match = re.search(r'<img[^>]*src="([^"]+)"', item, re.DOTALL)  
-            if img_match:  
-                url = img_match.group(1)  
-                stories.append({  
-                    "id": f"picuki_{len(stories)}",  
-                    "type": "image",  
-                    "url": url,  
-                    "timestamp": datetime.now().isoformat(),  
-                })  
-            
-            # Try to extract video URL  
-            video_match = re.search(r'<video[^>]*>.*?<source[^>]*src="([^"]+)"', item, re.DOTALL)  
-            if video_match:  
-                url = video_match.group(1)  
-                stories.append({  
-                    "id": f"picuki_{len(stories)}",  
-                    "type": "video",  
-                    "url": url,  
-                    "timestamp": datetime.now().isoformat(),  
-                })  
-        
-        if not stories:  
-            logger.info(f"No story media found on Picuki for {username}")  
-            return None  
-        
-        result = {  
-            "data": stories,  
-            "count": len(stories),  
-            "username": username,  
-            "source": "picuki",  
-            "fetched_at": datetime.now().isoformat()  
+        if response.status_code == 200:  
+            data = response.json()  
+            if 'reel' in data and 'items' in data['reel'] and data['reel']['items']:  
+                logger.info(f"Successfully got stories via direct API for {username}")  
+                # Process items and return  
+                stories = []  
+                for item in data['reel']['items']:  
+                    story = {  
+                        "id": item.get('pk', ''),  
+                        "type": "video" if item.get('media_type') == 2 else "image",  
+                        "timestamp": datetime.fromtimestamp(item.get('taken_at')).isoformat()  
+                    }  
+                    
+                    if story["type"] == "video" and 'video_versions' in item and item['video_versions']:  
+                        story["url"] = item['video_versions'][0]['url']  
+                    elif 'image_versions2' in item and 'candidates' in item['image_versions2'] and item['image_versions2']['candidates']:  
+                        story["url"] = item['image_versions2']['candidates'][0]['url']  
+                    else:  
+                        continue  # Skip if no URL  
+                        
+                    stories.append(story)  
+                
+                if stories:  
+                    return {  
+                        "data": stories,  
+                        "count": len(stories),  
+                        "username": username,  
+                        "source": "instagram_api",  
+                        "fetched_at": datetime.now().isoformat()  
+                    }  
+    except Exception as e:  
+        logger.warning(f"Direct API access failed: {str(e)}")  
+    
+    # Try method 2: Unofficial service (if available)  
+    try:  
+        logger.info(f"Attempting unofficial service for {username}")  
+        url = f"https://instagram-stories1.p.rapidapi.com/v1/get_stories?username={username}"  
+        headers = {  
+            "X-RapidAPI-Key": os.getenv('RAPIDAPI_KEY', ''),  # Set this in your environment if available  
+            "X-RapidAPI-Host": "instagram-stories1.p.rapidapi.com"  
         }  
         
-        return result  
-        
+        if headers["X-RapidAPI-Key"]:  # Only try if API key is set  
+            response = requests.get(url, headers=headers, timeout=10)  
+            
+            if response.status_code == 200:  
+                data = response.json()  
+                if isinstance(data, dict) and 'stories' in data and data['stories']:  
+                    logger.info(f"Successfully got stories via unofficial service for {username}")  
+                    stories = []  
+                    
+                    for item in data['stories']:  
+                        story = {  
+                            "id": item.get('id', str(hash(item.get('media_url', '')))),  
+                            "type": item.get('media_type', 'image'),  
+                            "url": item.get('media_url', ''),  
+                            "timestamp": item.get('timestamp', datetime.now().isoformat())  
+                        }  
+                        stories.append(story)  
+                    
+                    if stories:  
+                        return {  
+                            "data": stories,  
+                            "count": len(stories),  
+                            "username": username,  
+                            "source": "unofficial_api",  
+                            "fetched_at": datetime.now().isoformat()  
+                        }  
     except Exception as e:  
-        logger.error(f"Error fetching from Picuki: {str(e)}")  
-        return None  
+        logger.warning(f"Unofficial service failed: {str(e)}")  
+    
+    # All methods failed  
+    return None  
 
 @app.get("/stories/{username}")  
 async def get_stories(username: str, cached: bool = False, demo: bool = False):  
@@ -243,13 +251,13 @@ async def get_stories(username: str, cached: bool = False, demo: bool = False):
                 save_to_cache(username, demo_stories, minutes=5)  # Short cache time for demo content  
                 return {**demo_stories, "rate_limited": True}  
         
-        # Try to get stories from Picuki  
-        result = get_picuki_stories(username)  
+        # Try to get real stories  
+        real_stories = try_get_real_stories(username)  
         
-        if result:  
+        if real_stories:  
             # Cache the successful result  
-            save_to_cache(username, result)  
-            return result  
+            save_to_cache(username, real_stories)  
+            return real_stories  
         
         # If no result, check cache  
         cached_result = get_cached_stories(username)  
@@ -260,7 +268,7 @@ async def get_stories(username: str, cached: bool = False, demo: bool = False):
         # No result and no cache, use demo content  
         demo_stories = get_demo_stories(username)  
         save_to_cache(username, demo_stories, minutes=30)  
-        return {**demo_stories, "no_live_stories": True}  
+        return demo_stories  
         
     except Exception as e:  
         error_message = str(e)  
@@ -274,7 +282,6 @@ async def get_stories(username: str, cached: bool = False, demo: bool = False):
         
         # No cache available, use demo content  
         demo_stories = get_demo_stories(username)  
-        save_to_cache(username, demo_stories, minutes=10)  
         return {**demo_stories, "error_occurred": True}  
 
 @app.get("/download/{url:path}")  
@@ -328,6 +335,23 @@ async def download_media(url: str):
             detail="Failed to download media"  
         )  
 
+# Add an endpoint to explain what's happening  
+@app.get("/")  
+async def root():  
+    return {  
+        "message": "Instagram Stories API",  
+        "status": "Running with demo mode",  
+        "note": "Due to Instagram's API restrictions, this service currently provides placeholder content.",  
+        "endpoints": {  
+            "get_stories": "/stories/{username}",  
+            "get_stories_from_cache": "/stories/{username}?cached=true",  
+            "get_demo_stories": "/stories/{username}?demo=true",  
+            "download_media": "/download/{url}",  
+            "health_check": "/health"  
+        },  
+        "timestamp": datetime.now().isoformat()  
+    }  
+
 # Load cache from disk at startup  
 @app.on_event("startup")  
 def load_cache_from_disk():  
@@ -359,6 +383,8 @@ def load_cache_from_disk():
 async def health_check():  
     return {  
         "status": "ok",   
+        "mode": "demo",  
+        "note": "Instagram access restricted - using placeholder content",  
         "timestamp": datetime.now().isoformat(),  
         "cache_size": len(STORY_CACHE),  
     }